@botbotgo/better-call 0.1.13 → 0.1.14

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +21 -17
  2. package/benchmarks/bfcl-real-remote-completed-summary.json +119 -1
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -4,7 +4,7 @@
4
4
 
5
5
  # BetterCall
6
6
 
7
- **One-line wrapper. Seven full BFCL remote runs completed. Best: 73.4% → 83.8%.**
7
+ **One-line wrapper. Eight full BFCL remote runs completed. Best: 73.4% → 83.8%.**
8
8
 
9
9
  ```ts
10
10
  const tools = betterTools([searchTool, calculatorTool]);
@@ -142,6 +142,9 @@ qwen3.5:2b
142
142
  lfm2.5-thinking:latest
143
143
  Raw 50.8% | ####################....................
144
144
  BetterCall 54.8% | ######################..................
145
+ qwen3.5:4b
146
+ Raw 43.6% | #################.......................
147
+ BetterCall 43.4% | #################.......................
145
148
  gemma4:e2b
146
149
  Raw 24.3% | ##########..............................
147
150
  BetterCall 24.7% | ##########..............................
@@ -155,26 +158,27 @@ gemma4:e2b
155
158
  | 4 | `qwen3.5:0.8b` | 3,625 | 54.6% | 56.9% | +2.3pp | 901 |
156
159
  | 5 | `qwen3.5:2b` | 3,625 | 53.9% | 54.9% | +1.0pp | 1,308 |
157
160
  | 6 | `lfm2.5-thinking:latest` | 3,625 | 50.8% | 54.8% | +4.0pp | 1,142 |
158
- | 7 | `gemma4:e2b` | 3,625 | 24.3% | 24.7% | +0.4pp | 2,641 |
161
+ | 7 | `qwen3.5:4b` | 3,625 | 43.6% | 43.4% | -0.2pp | 1,847 |
162
+ | 8 | `gemma4:e2b` | 3,625 | 24.3% | 24.7% | +0.4pp | 2,641 |
159
163
 
160
- Latest completed model category detail: `qwen2.5:7b-instruct`.
164
+ Latest completed model category detail: `qwen3.5:4b`.
161
165
 
162
166
  | Category | Cases | Raw | BetterCall repair | Lift | Request errors |
163
167
  | --- | ---: | ---: | ---: | ---: | ---: |
164
- | `simple_python` | 400 | 91.3% | 93.0% | +1.8pp | 9 |
165
- | `simple_java` | 100 | 55.0% | 59.0% | +4.0pp | 3 |
166
- | `simple_javascript` | 50 | 60.0% | 64.0% | +4.0pp | 0 |
167
- | `multiple` | 200 | 89.5% | 91.0% | +1.5pp | 3 |
168
- | `parallel` | 200 | 81.0% | 84.5% | +3.5pp | 2 |
169
- | `parallel_multiple` | 200 | 77.0% | 78.0% | +1.0pp | 6 |
170
- | `irrelevance` | 240 | 64.6% | 89.6% | +25.0pp | 0 |
171
- | `live_simple` | 258 | 69.0% | 72.1% | +3.1pp | 1 |
172
- | `live_multiple` | 1,053 | 69.0% | 73.4% | +4.4pp | 18 |
173
- | `live_parallel` | 16 | 25.0% | 37.5% | +12.5pp | 2 |
174
- | `live_parallel_multiple` | 24 | 50.0% | 50.0% | +0.0pp | 2 |
175
- | `live_irrelevance` | 884 | 67.6% | 75.9% | +8.3pp | 34 |
176
-
177
- The strongest `qwen2.5:7b-instruct` category lift was `irrelevance`, improving from 64.6% to 89.6%. The largest absolute live gain was `live_irrelevance`, improving by 73 cases.
168
+ | `simple_python` | 400 | 81.3% | 81.3% | +0.0pp | 54 |
169
+ | `simple_java` | 100 | 56.0% | 56.0% | +0.0pp | 32 |
170
+ | `simple_javascript` | 50 | 48.0% | 48.0% | +0.0pp | 18 |
171
+ | `multiple` | 200 | 83.5% | 83.5% | +0.0pp | 20 |
172
+ | `parallel` | 200 | 70.0% | 70.0% | +0.0pp | 45 |
173
+ | `parallel_multiple` | 200 | 47.0% | 47.0% | +0.0pp | 96 |
174
+ | `irrelevance` | 240 | 68.8% | 68.8% | +0.0pp | 75 |
175
+ | `live_simple` | 258 | 66.7% | 66.3% | -0.4pp | 45 |
176
+ | `live_multiple` | 1,053 | 41.6% | 41.0% | -0.6pp | 538 |
177
+ | `live_parallel` | 16 | 0.0% | 0.0% | +0.0pp | 16 |
178
+ | `live_parallel_multiple` | 24 | 0.0% | 0.0% | +0.0pp | 24 |
179
+ | `live_irrelevance` | 884 | 0.0% | 0.0% | +0.0pp | 884 |
180
+
181
+ This `qwen3.5:4b` run hit sustained remote request failures in the live categories; those failures are counted as incorrect by the benchmark.
178
182
 
179
183
  Historical targeted wrapper benchmark:
180
184
 
package/benchmarks/bfcl-real-remote-completed-summary.json CHANGED
@@ -2,7 +2,7 @@
2
2
  "name": "BFCL v4 full remote Ollama runs",
3
3
  "source": "Real model calls against all supported BFCL v4 single-turn tool-call categories completed in this repository",
4
4
  "note": "Endpoint redacted. Scores count request errors/timeouts as incorrect. This is not an official BFCL leaderboard submission.",
5
- "generatedAt": "2026-05-08T22:24:15.073Z",
5
+ "generatedAt": "2026-05-09T01:31:12.909Z",
6
6
  "results": [
7
7
  {
8
8
  "model": "granite4.1:3b",
@@ -712,6 +712,124 @@
712
712
  }
713
713
  ]
714
714
  },
715
+ {
716
+ "model": "qwen3.5:4b",
717
+ "total": 3625,
718
+ "rawCorrect": 1581,
719
+ "betterCorrect": 1574,
720
+ "errors": 1847,
721
+ "repaired": 0,
722
+ "categories": [
723
+ {
724
+ "model": "qwen3.5:4b",
725
+ "category": "simple_python",
726
+ "total": 400,
727
+ "rawCorrect": 325,
728
+ "betterCorrect": 325,
729
+ "errors": 54,
730
+ "repaired": 0
731
+ },
732
+ {
733
+ "model": "qwen3.5:4b",
734
+ "category": "simple_java",
735
+ "total": 100,
736
+ "rawCorrect": 56,
737
+ "betterCorrect": 56,
738
+ "errors": 32,
739
+ "repaired": 0
740
+ },
741
+ {
742
+ "model": "qwen3.5:4b",
743
+ "category": "simple_javascript",
744
+ "total": 50,
745
+ "rawCorrect": 24,
746
+ "betterCorrect": 24,
747
+ "errors": 18,
748
+ "repaired": 0
749
+ },
750
+ {
751
+ "model": "qwen3.5:4b",
752
+ "category": "multiple",
753
+ "total": 200,
754
+ "rawCorrect": 167,
755
+ "betterCorrect": 167,
756
+ "errors": 20,
757
+ "repaired": 0
758
+ },
759
+ {
760
+ "model": "qwen3.5:4b",
761
+ "category": "parallel",
762
+ "total": 200,
763
+ "rawCorrect": 140,
764
+ "betterCorrect": 140,
765
+ "errors": 45,
766
+ "repaired": 0
767
+ },
768
+ {
769
+ "model": "qwen3.5:4b",
770
+ "category": "parallel_multiple",
771
+ "total": 200,
772
+ "rawCorrect": 94,
773
+ "betterCorrect": 94,
774
+ "errors": 96,
775
+ "repaired": 0
776
+ },
777
+ {
778
+ "model": "qwen3.5:4b",
779
+ "category": "irrelevance",
780
+ "total": 240,
781
+ "rawCorrect": 165,
782
+ "betterCorrect": 165,
783
+ "errors": 75,
784
+ "repaired": 0
785
+ },
786
+ {
787
+ "model": "qwen3.5:4b",
788
+ "category": "live_simple",
789
+ "total": 258,
790
+ "rawCorrect": 172,
791
+ "betterCorrect": 171,
792
+ "errors": 45,
793
+ "repaired": 0
794
+ },
795
+ {
796
+ "model": "qwen3.5:4b",
797
+ "category": "live_multiple",
798
+ "total": 1053,
799
+ "rawCorrect": 438,
800
+ "betterCorrect": 432,
801
+ "errors": 538,
802
+ "repaired": 0
803
+ },
804
+ {
805
+ "model": "qwen3.5:4b",
806
+ "category": "live_parallel",
807
+ "total": 16,
808
+ "rawCorrect": 0,
809
+ "betterCorrect": 0,
810
+ "errors": 16,
811
+ "repaired": 0
812
+ },
813
+ {
814
+ "model": "qwen3.5:4b",
815
+ "category": "live_parallel_multiple",
816
+ "total": 24,
817
+ "rawCorrect": 0,
818
+ "betterCorrect": 0,
819
+ "errors": 24,
820
+ "repaired": 0
821
+ },
822
+ {
823
+ "model": "qwen3.5:4b",
824
+ "category": "live_irrelevance",
825
+ "total": 884,
826
+ "rawCorrect": 0,
827
+ "betterCorrect": 0,
828
+ "errors": 884,
829
+ "repaired": 0
830
+ }
831
+ ]
832
+ },
715
833
  {
716
834
  "model": "gemma4:e2b",
717
835
  "total": 3625,
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@botbotgo/better-call",
3
- "version": "0.1.13",
3
+ "version": "0.1.14",
4
4
  "description": "LLM tool-call reliability layer.",
5
5
  "type": "module",
6
6
  "license": "Apache-2.0",